Derrick Hang February 24, 2010 Economics 201FS

Slides:



Advertisements
Similar presentations
January 6. January 7 January 8 January 9 January 10.
Advertisements

Lecture 28 Categorical variables: –Review of slides from lecture 27 (reprint of lecture 27 categorical variables slides with typos corrected) –Practice.
Jumps in High Volatility Environments and Extreme Value Theory Abhinay Sawant March 4, 2009 Economics 201FS.
WFC & ORCL David Kim Data ORCL (Oracle Corporation) – April 16, 1997 – Dec 30, 2010 WFC (Wells Fargo Corporation) – April 9, 1997 – Dec 30, 2010.
Preliminary Data analysis Pat Amatyakul Econ 201 FS 4 February 2009.
Realized Beta: Market vs. Individual stocks Angela Ryu Economics 201FS Honors Junior Workshop: Finance Duke University March 17, 2010.
Forecasting Outside the Range of the Explanatory Variable: Chapter
BOX JENKINS METHODOLOGY
1 DSCI 3023 Linear Regression Outline Linear Regression Analysis –Linear trend line –Regression analysis Least squares method –Model Significance Correlation.
Math 15 Introduction to Scientific Data Analysis Lecture 6 Interactive Excel University of California, Merced.
Derrick Hang February 10, 2010 Economics 201FS. Apple Inc. (AAPL): January 16, 1997 – January 7, ,920 Days IBM (IBM): April 9, 1997 – January 7,
Jump Detection and Analysis Investigation of Media/Telecomm Industry Prad Nadakuduty Presentation 3 3/5/08.
Initial Data Analysis Kunal Jain February 17, 2010 Economics 201FS.
Modeling Real World Data: Scatter Plots. Key Topics Bivariate Data: data that contains two variables Scatter Plot: a set of bivariate data graphed as.
1 CHAPTER 15 FINANCIAL APPLICATIONS OF TIME-VARYING VOLATILITY Figure 15.1 Value-at-Risk González-Rivera: Forecasting for Economics and Business, Copyright.
Examining Relationships in Quantitative Research
2.5 Using Linear Models A scatter plot is a graph that relates two sets of data by plotting the data as ordered pairs. You can use a scatter plot to determine.
SunSatFriThursWedTuesMon January
Initial Stock Analysis Andrew Bentley February 8, 2012.
Unit 3 Section : Regression  Regression – statistical method used to describe the nature of the relationship between variables.  Positive.
40 Minutes Left.
Beta Prediction: Optimal Number of Observations and Liquidity Angela Ryu Economics 201FS Honors Junior Workshop: Finance Duke University April 14, 2010.
Mass / g Time / min
High Frequency Data Analysis Sharon Lee Econ 201 FS February 4, 2009.
Chapter 20 Time Series Analysis and Forecasting. Introduction Any variable that is measured over time in sequential order is called a time series. We.
Time-Varying Beta: Heterogeneous Autoregressive Beta Model Kunal Jain Spring 2010 Economics 201FS May 5, 2010.
Analysis of financial data Anders Lundquist Spring 2010.
Jump Correlation within an Industry – A Beginning By: Zed Lamba ECON 201FS.
Chapter 4: Production and the Costs of Production
Bayesian modeling and analysis of stochastic volatility in finance
Jump Detection and Analysis Investigation of Media/Telecomm Industry
The Effects of Quarterly Earnings on Volatility and Jumps
High-Frequency Analysis of WFC and PFE
Crooked Oak Middle School Spring Incentive Program 2018
Non-linear and Multiple Regression
HAR-RV with Sector Variance
Cumulative Frequency Curves
Macroeconomic Effects on Stock Jumps
Economics 201FS: Jump Test, Covariance on jump and non-jump intervals
Data Analysis II Mingwei Lei March 3rd, 2010 Econ 201S.
Econ201FS- New Jump Test Haolan Cai.
Preliminary Data Analysis
ECON 201FS MSFT Daily Realized Variance: Factor Analysis and Time-Lagged Regressions By: Zed Lamba.
Jump Detection and Analysis Investigation of Media/Telecomm Industry
EMPIRICAL STUDY AND FORECASTING (II)
Initial Analysis Siyu Zheng.
Preliminary Data Analysis
15 seconds left 30 seconds left 3 minutes left 2 minutes left 1 minute
Kunal Jain February 17, 2010 Economics 201FS
Stochastic Volatility Model: High Frequency Data
Formulating a Research Topic
Jump Processes and Trading Volume
Econ 201 FS April 8, 2009 Pongpitch Amatyakul
Kunal Jain March 24, 2010 Economics 201FS
Comparing MSE: Optimal Sampling Frequency and Beta Interval
Initial Stock Analysis
Preliminary Data Analysis
Initial Data Analysis Mingwei Lei.
Jump Detection and Analysis Investigation of Media/Telecomm Industry
Deeper exploration of volume and Jump statistics
Chapter 13 Additional Topics in Regression Analysis
Preliminary Data Analysis
Regression and Categorical Predictors
Second Attempt at Jump-Detection and Analysis
Presentation 2 Siyu Zheng.
MSFT GE About the Stocks April 16, 1997 – January 25, days
“Day D” February 6, :51 - 8:51 Exploratory 8:53 - 9:53
Sampling Frequency and Jump Detection
Adaptive Variable Selection
Presentation transcript:

Derrick Hang February 24, 2010 Economics 201FS Data Analysis II Derrick Hang February 24, 2010 Economics 201FS

Corrections: The Data Apple Inc. (AAPL): April 16, 1997 – January 7, 2009 2,920 Days IBM (IBM): April 9, 1997 – January 7, 2009 2,925 Days Proctor Gamble Co (PG): 2,924 Days * *Absence of a day from PG was found to be on March 7, 2000; this is when PG released a warning that earnings for the rest of the fiscal year will fall short of expectations, contributing 142 to the 374 point drop in the Dow that day

Modifications 8 minute intervals are used so the intervals fit exactly with the 385 minutes per day window; in other words, there is no incomplete interval left over at the end of each day i.e. to obtain the first 8-minute return you take the price level at the 1st min. and the 9th min., then the 9th and the 15th, etc.; following this sequence, we end up using the price level at the 385th and 377th min. 8 minute is consistent with the volatility signature plots presented last time, and leaves no incomplete interval at the end

Returns for 8-minute intervals

Corrected MA TP Jump test

Corrected MA TP Jump test IBM 0.1% Significance Level = 75 / 2925 (2.56%) 1% Significance Level = 219 / 2925 (7.49%) 5% Significance Level = 539 / 2925 (18.43%) PG 0.1% Significance Level = 82 / 2924 (2.80%) 1% Significance Level = 223 / 2924 (7.63%) 5% Significance Level = 548 / 2924 (18.74%) AAPL 0.1% Significance Level = 113 / 2920 (3.87%) 1% Significance Level = 305 / 2920 (10.45%) 5% Significance Level = 625 / 2920 (21.40%)

Corrected MA QP Jump test

Corrected MA QP Jump test IBM 0.1% Significance Level = 80 / 2925 (2.74%) 1% Significance Level = 236 / 2925 (8.07%) 5% Significance Level = 559 / 2925 (19.11%) PG 0.1% Significance Level = 94 / 2924 (3.21%) 1% Significance Level = 238 / 2924 (8.14%) 5% Significance Level = 563 / 2924 (19.25%) AAPL 0.1% Significance Level = 136 / 2920 (4.66%) 1% Significance Level = 326 / 2920 (11.16%) 5% Significance Level = 653 / 2920 (22.36%)

AAPL Jump Detection: Median Test 0.1% Significance Level = 65 / 2920 (2.23%) 1% Significance Level = 143 / 2920 (4.90%) 5% Significance Level = 328 / 2920 (11.23%)

IBM Jump Detection: Median Test 0.1% Significance Level = 57 / 2925 (1.95%) 1% Significance Level = 126 / 2925 (4.31%) 5% Significance Level = 278 / 2925 (9.50%)

PG Jump Detection: Median Test 0.1% Significance Level = 61 / 2924 (2.09%) 1% Significance Level = 143 / 2924 (4.89%) 5% Significance Level = 285 / 2924 (9.75%)

Exploring topics: Forecasting Bayesian Forecasting with Dynamic Models using high-frequency data Regression where every variable varies with time Better coefficients from use of high frequency data? What time window has better predictability? What should be the dependent: returns, prices, volatility?